Common method variance or measurement bias? The problem and possible solutions

Publisher: Sage
    • "We do not resolve this dispute in our research, because other papers handle this discussion very well. See, for example, Spector and Brannick (2009) or Podsakoff et al. (2003). Overall, our research is well aligned with the perspective that a method is a mechanism where by an item triggers unrelated personality traits within the respondent. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This research analyzes the effects of common method variance (CMV) on parameter estimates in bivariate linear, multivariate linear, quadratic, and interaction regression models. The authors demonstrate that CMV can either inflate or deflate bivariate linear relationships, depending on the degree of symmetry with which CMV affects the observed measures. With respect to multivariate linear relationships, they show that common method bias generally decreases when additional independent variables suffering from CMV are included in a regression equation. Finally, they demonstrate that quadratic and interaction effects cannot be artifacts of CMV. On the contrary, both quadratic and interaction terms can be severely deflated through CMV, making them more difficult to detect through statistical means.
    Organizational Research Methods 07/2010; 13(3):456-476. DOI:10.1177/1094428109351241 · 3.26 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: During the past decade, considerable research attention has been given to core self-evaluations (CSEs). Although this research has found that CSE is related to several important work-related outcomes (e.g., job satisfaction, job performance), we believe that researchers’ reliance on general rather than work-specific CSE has resulted in underestimates of the importance of CSE. Based on the literature on frame-of-reference effects in personality assessment, we predict that work-related CSE will yield stronger relationships with work-related criteria than general CSE will and that work-specific CSE will be related to work-specific criteria after general CSE has been controlled. Using two independent samples, we found that when compared with general CSE, work-specific CSE generally failed to yield significantly stronger zero-order relationships with work-related criteria. However, we found several instances in which work-specific CSE predicted incremental variance in work-related criteria after the effects of general CSE were controlled.
    Journal of Vocational Behavior 06/2010; 76(3):559-566. DOI:10.1016/j.jvb.2010.01.008 · 2.03 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Several studies in the organisational citizenship behavior (OCB) literature have focused on the main effects of employee dispositions and job attitudes. The current study builds upon previous findings by examining whether core self‐evaluations (CSE) moderate the relationship between job attitudes and OCBs. Consistent with our hypotheses and with the notion that CSE contributes to one's general level of initiative and self‐confidence, data collected from 200 New Zealand workers found that the job attitude–OCB relationship was stronger for workers who were high in CSE than for workers who were low in CSE.
    Applied Psychology 01/2012; 61(1). DOI:10.1111/j.1464-0597.2011.00458.x · 1.52 Impact Factor
Show more